Wan 3.0 Video API: Latest-Gen Text & Image to Video

Overview

Wan 3.0 Video generates videos from prompts, first-frame or first-and-last-frame images, and multimodal reference inputs such as images, videos, audio files, files, and web links. Use this page when you are ready to call the API after trying the model in the APIXO playground.

Capability	Value
Model ID	`wan-3-0-video`
Modes	`text-to-video`, `image-to-video`, `reference-to-video`
Prompt	Required for `text-to-video`; optional for `image-to-video` and `reference-to-video`
Resolutions	`480p`, `720p`, `1080p`
Aspect ratios	`auto`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`
Duration	`-1` for smart duration, or any integer from `2` through `30` seconds; defaults to `5`
Image-to-video images	1-2 image URLs; the second image is the optional last frame
Reference inputs	Up to 10 image URLs, 5 video URLs, 5 audio URLs, 1 file URL, or 1 link URL
Result format	MP4 URL array in `resultJson.resultUrls`

Choose the Wan 3.0 endpoint

All three endpoints support text-to-video, first-frame or first-and-last-frame image-to-video, and reference-to-video. Choose the endpoint before copying its parameters or price:

Endpoint	Output resolutions	Reference-to-video inputs
Wan 3.0 Video	`480p`, `720p`, `1080p`	Images, video, audio, plus at most one file URL or one web link; file and link inputs are mutually exclusive
Wan 3.0 Video LoRA	`480p`, `720p`, `1080p`	Images, video, and audio; no `file_urls` or `link_urls`
Wan 3.0 Video Pro LoRA	`1080p`, `2k`, `4k`	Images, video, and audio; no `file_urls` or `link_urls`

For workflow selection, see the Wan 3.0 Video, LoRA, and Pro LoRA comparison. Use the selected endpoint’s rate from API Pricing, even when two endpoints offer the same resolution.

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/wan-3-0-video`	Submit a generation task
`GET`	`/statusTask/wan-3-0-video?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request submits a text-to-video task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-3-0-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic product reveal with smooth camera movement and premium studio lighting",
      "resolution": "480p",
      "aspect_ratio": "auto",
      "duration": 5,
      "sound": true
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/wan-3-0-video?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965790929,
    "costTime": 180000
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "UPSTREAM_ERROR",
    "failMsg": "Generation failed",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;

Request body

Text-to-video

{
  "request_type": "async",
  "input": {
    "mode": "text-to-video",
    "prompt": "a serene lake at sunrise with a slow cinematic camera move",
    "resolution": "480p",
    "aspect_ratio": "16:9",
    "duration": 6,
    "sound": true,
    "watermark": false
  }
}

Image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "prompt": "animate this portrait with subtle head movement and cinematic lighting",
    "image_urls": [
      "https://example.com/first-frame.png",
      "https://example.com/last-frame.png"
    ],
    "resolution": "720p",
    "aspect_ratio": "auto",
    "duration": 5,
    "sound": true
  }
}

Reference-to-video

{
  "request_type": "async",
  "input": {
    "mode": "reference-to-video",
    "prompt": "keep the subject identity and create a natural speaking video",
    "image_urls": [
      "https://example.com/person.png"
    ],
    "video_urls": [
      "https://example.com/motion-reference.mp4"
    ],
    "file_urls": [
      "https://example.com/profile.pdf"
    ],
    "resolution": "720p",
    "aspect_ratio": "auto",
    "duration": -1,
    "sound": true,
    "watermark": false
  }
}

Parameters

string

default:"async"

Result delivery mode. Omit this field or use async for polling with statusTask, or use callback for webhook delivery.

string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

object

required

Wan 3.0 Video input parameters.

Show properties

string

required

Generation mode. Supported values: text-to-video, image-to-video, reference-to-video. Reference-to-video requires at least one supported reference input; see the mode table below.

string

Prompt text. Required for text-to-video; optional for image-to-video and reference-to-video. Required prompts cannot be empty after trimming. Maximum length: 20000 characters.

string

default:"1080p"

Output resolution tier. Supported values: 480p, 720p, 1080p.

string

default:"auto"

Output aspect ratio. Supported values: auto, 16:9, 4:3, 1:1, 3:4, 9:16. Use aspect_ratio, not ratio.

integer|string

default:"5"

Output duration in seconds. Supports -1 for smart duration, or integers from 2 through 30, including numeric strings such as "8". Decimal values such as -1.0 are rejected.

boolean

default:"true"

Whether the generated video should include audio.

boolean

default:"false"

Whether to add a watermark.

integer

Optional random seed. Supported range: 0 to 2147483647. A fixed seed improves reproducibility, but identical seeds do not guarantee identical outputs.

string[]

Image URLs. Required for image-to-video with 1-2 images, where image_urls[0] is the first frame and image_urls[1] is the optional last frame. Optional for reference-to-video with up to 10 images.

string[]

Reference video URLs for reference-to-video. Supports up to 5 URLs when provided. Each video must be 1-15 seconds, total reference video duration cannot exceed 15 seconds, and reference video seconds are billed at the same per-second rate as the selected mode and resolution.

string[]

Reference audio URLs for reference-to-video. Supports up to 5 URLs when provided. Each audio file must be 1-15 seconds, and total reference audio duration cannot exceed 15 seconds. Audio is not billed separately.

string[]

File inputs for reference-to-video. Supports at most 1 URL. Cannot be used together with link_urls.

string[]

Web link inputs for reference-to-video. Supports at most 1 URL. Cannot be used together with file_urls.

Mode	Required input	Unsupported media fields	Billing note
`text-to-video`	`prompt`	`image_urls`, `video_urls`, `audio_urls`, `file_urls`, `link_urls`	Output duration is billed per second.
`image-to-video`	`image_urls` with 1-2 images	`video_urls`, `audio_urls`, `file_urls`, `link_urls`	Output duration is billed per second.
`reference-to-video`	At least one of `image_urls`, `video_urls`, `audio_urls`, `file_urls`, or `link_urls`	None, but `file_urls` and `link_urls` are mutually exclusive	Output duration and reference video seconds are billed per second.

Use public, directly accessible URLs for all media inputs. Video and audio durations are checked before the task is submitted.

When duration is positive and video_urls are provided, total reference video seconds plus duration cannot exceed 30 seconds. When duration is -1, the request uses smart duration and is pre-charged as input video seconds plus 30 output seconds.

For guidance on choosing and combining references, see the Wan 3.0 reference workflow.

Response format

Submit task response

POST /generateTask/wan-3-0-video returns a task ID when the task is accepted:

integer

API status code. 200 means the task was accepted.

string

Human-readable status message.

string

Unique task identifier used with the status endpoint.

Status response fields

string

Unique task identifier.

string

Current task state: processing, success, or failed.

string

JSON string containing generated video URLs in resultUrls. Present when state is success.

string

Machine-readable failure code. Present when state is failed.

string

Human-readable failure message. Present when state is failed.

integer

Task creation timestamp in Unix milliseconds.

integer

Task completion timestamp in Unix milliseconds. Present after completion.

integer

Processing duration in milliseconds. Present after completion when timing data is available.

object

Final billing snapshot. Present only on successful terminal responses for wan-3-0-video tasks submitted with duration=-1.

string

Settlement status. For this final snapshot the value is always final.

number

Total duration of all input videos, in seconds, rounded half up to 3 decimal places.

number

Actual generated output video duration, in seconds, rounded half up to 3 decimal places.

number

Final billable duration in seconds. This is always inputVideoSeconds + outputVideoSeconds.

string

Duration unit. The value is second.

string

Rounding rule used for duration fields. The value is round half up to 3 decimal places.

integer

Number of input videos included in inputVideoSeconds.

integer

Number of output videos included in outputVideoSeconds.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-3-0-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "reference-to-video",
      "prompt": "create a polished product video using the references",
      "image_urls": [
        "https://example.com/ref.png"
      ],
      "resolution": "720p",
      "aspect_ratio": "auto",
      "duration": -1,
      "sound": true
    }
  }'

The callback payload uses the same top-level shape as status polling with code, message, and data. Successful callbacks include the final state and resultJson. For duration=-1 tasks, successful terminal callbacks include the same data.billing object returned by status polling. See Webhooks for delivery requirements and retry behavior.

Billing

Market display references equal the standard APIXO price multiplied by 1.30, rounded half up to three decimal places. They are comparison values, not live third-party quotes or the charged amount. New non-LLM requests use 1 credit = $0.001. Calculate the full amount, including billable quantity and add-ons, apply the applicable account discount, then round the request total upward to the next whole credit. Agreed fixed unit prices retain their precision and replace the standard price and discount; final rounding still applies. See credit conversion and rounding. Wan 3.0 Video is billed per second. All three generation modes share the same unit price for a given resolution. Reference-to-video bills output seconds plus the actual input reference video seconds at that same unit price.

Mode	Resolution	APIXO official price	Market display reference
`text-to-video`	`480p`	`$0.05 / second`	`$0.065 / second`
`text-to-video`	`720p`	`$0.10 / second`	`$0.130 / second`
`text-to-video`	`1080p`	`$0.20 / second`	`$0.260 / second`
`image-to-video`	`480p`	`$0.05 / second`	`$0.065 / second`
`image-to-video`	`720p`	`$0.10 / second`	`$0.130 / second`
`image-to-video`	`1080p`	`$0.20 / second`	`$0.260 / second`
`reference-to-video`	`480p`	`$0.05 / second`	`$0.065 / second`
`reference-to-video`	`720p`	`$0.10 / second`	`$0.130 / second`
`reference-to-video`	`1080p`	`$0.20 / second`	`$0.260 / second`

Billing formulas:

Request	Formula
`text-to-video` or `image-to-video` with positive `duration`	`duration * unitPrice`
`reference-to-video` with positive `duration`	`(input video seconds + duration) * unitPrice`
Any mode with `duration = -1`	Pre-charge `(input video seconds + 30) * unitPrice`; after success, final billable seconds are `input video seconds + actual output seconds`, and any difference is refunded

Input images, audio files, files, and links do not add separate billable seconds. Successful terminal duration=-1 responses return the final settled seconds under data.billing. The following illustrative snapshot uses one 5.371-second reference video and one 10.042-second output; it is not a measured task result:

{
  "billing": {
    "settlementState": "final",
    "inputVideoSeconds": 5.371,
    "outputVideoSeconds": 10.042,
    "totalBillableSeconds": 15.413,
    "unit": "second",
    "rounding": "round half up to 3 decimal places",
    "inputVideoCount": 1,
    "outputVideoCount": 1
  }
}

All duration fields in billing use seconds and are rounded half up to 3 decimal places. inputVideoSeconds is the sum of all input video durations, and inputVideoCount is the number of input videos included in that sum. outputVideoSeconds is the actual generated output duration. totalBillableSeconds is always inputVideoSeconds + outputVideoSeconds. Without input videos, inputVideoSeconds is 0.000 and inputVideoCount is 0. This billing object appears only after successful final settlement, is also included in successful callback payloads, and remains stable on repeated polling. Without reference video, input video seconds are zero. Reference-to-video still requires at least one supported reference input. For duration=-1, the 30 output seconds are a pre-charge basis, not a promised output length. The final charge is (input video seconds + actual output seconds) * unitPrice; use the successful response with data.billing.settlementState=final for settled seconds. For example, using the documented 1080p base rate of $0.20/second, a 5-second reference video and a fixed 10-second output cost $3.00. With duration=-1, the same input is initially charged (5 + 30) * $0.20 = $7.00. If the successful output is 10 seconds, the final charge is $3.00 and the difference refunded is $4.00. These are arithmetic examples, not measured generation results. For a budgeting walkthrough, see the Wan 3.0 duration and cost guide. Its dollar examples use standard Wan 3.0 Video rates; check API Pricing for your selected endpoint’s current rate. API usage is billed in USD separately from Studio monthly credits. For current API rates in USD, see API pricing.

Latency and polling

Wan 3.0 Video tasks are asynchronous. Actual latency may vary by prompt complexity, duration, reference media accessibility, resolution, route queue load, and generation time.

Workload	Typical generation time	Recommended first poll	Poll interval
Text-to-video or image-to-video	Varies by prompt, resolution, and duration	60s after task creation	10s-15s
Reference-to-video with image, video, audio, file, or link inputs	Often longer than simple generation	60s-90s after task creation	10s-15s

For production workloads, use callback mode to avoid frequent polling while video tasks run.

Result URLs are temporary. Download and store important outputs promptly after task completion. Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, missing `input`, unsupported `mode`, missing required `prompt` or media, invalid `resolution`, invalid `aspect_ratio`, invalid `duration`, or invalid media array	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`404`	Task not found when polling	Check the `taskId`
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error or unknown task failure	Retry with backoff
`502`	Service error	Retry with backoff
`504`	Service timeout	Retry or use callback mode for long-running jobs

Validation notes

Condition	Backend behavior
Missing `input`	Request fails before task creation.
Missing `mode`	Request fails before task creation.
Unsupported `mode`	Request fails before task creation. Supported values are `text-to-video`, `image-to-video`, and `reference-to-video`.
Missing `prompt` in `text-to-video`	Request fails before task creation.
Empty required `prompt`	Request fails before task creation.
Missing `resolution`	Defaults to `1080p`.
Unsupported `resolution`	Request fails before task creation. Supported values are `480p`, `720p`, and `1080p`.
Missing `aspect_ratio`	Defaults to `auto`.
Unsupported `aspect_ratio`	Request fails before task creation. Use `auto`, `16:9`, `4:3`, `1:1`, `3:4`, or `9:16`.
Using `ratio` instead of `aspect_ratio`	`ratio` is not a public Wan 3.0 field. Use `aspect_ratio`.
Missing `duration`	Defaults to `5`.
`duration` outside `-1` or `2` through `30`, or a decimal value	Request fails before task creation.
`image-to-video` without `image_urls`	Request fails before task creation.
`image-to-video` with more than 2 images	Request fails before task creation.
`reference-to-video` without any reference input	Request fails before task creation.
`file_urls` and `link_urls` used together	Request fails before task creation.
Reference video or audio shorter than 1 second or longer than 15 seconds	Request fails before task creation.
Total reference video duration or total reference audio duration over 15 seconds	Request fails before task creation.
Positive `duration` plus total reference video duration over 30 seconds	Request fails before task creation.

Task failure codes

failCode identifies the task failure. Common values include:

Fail code	Meaning	What to do
`SensitiveContent`	Prompt or input/output content was rejected by safety checks	Change the prompt or reference media
`PromptInvalid`	Prompt was invalid or rejected	Rewrite the prompt and retry
`ImageFormatIncorrect`	Reference image format could not be processed	Use a public, direct image URL in a common image format
`RateLimited`	A rate limit was reached	Retry with exponential backoff
`Timeout`	The task timed out	Retry later or use callback mode
`Unknown error`	An unknown task failure occurred	Retry with backoff or contact support with the `taskId`

See Error Codes for the full error reference.

MCP integration

The complete model schema declares result decoding in mcp.result and supported file bindings in mcp.attachments. These are client integration metadata, not generation input parameters. Attachment paths: image_urls, video_urls, audio_urls, file_urls. Preserve the user’s file order. Model parameter validation remains on the API.

​Overview

​Choose the Wan 3.0 endpoint

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-video

​Image-to-video

​Reference-to-video

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Validation notes

​Task failure codes

​MCP integration

​Related links

Overview

Choose the Wan 3.0 endpoint

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-video

Image-to-video

Reference-to-video

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Validation notes

Task failure codes

MCP integration

Related links